blob: 6fe9197f6ee44c54a726435da5a83ac4a7490ac1 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2007 Oracle. All rights reserved.
*/
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/radix-tree.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/workqueue.h>
#include <linux/kthread.h>
#include <linux/slab.h>
#include <linux/migrate.h>
#include <linux/ratelimit.h>
#include <linux/uuid.h>
#include <linux/semaphore.h>
#include <linux/error-injection.h>
#include <linux/crc32c.h>
#include <linux/sched/mm.h>
#include <asm/unaligned.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "volumes.h"
#include "print-tree.h"
#include "locking.h"
#include "tree-log.h"
#include "free-space-cache.h"
#include "free-space-tree.h"
#include "inode-map.h"
#include "check-integrity.h"
#include "rcu-string.h"
#include "dev-replace.h"
#include "raid56.h"
#include "sysfs.h"
#include "qgroup.h"
#include "compression.h"
#include "tree-checker.h"
#include "ref-verify.h"
#ifdef CONFIG_X86
#include <asm/cpufeature.h>
#endif
#define BTRFS_SUPER_FLAG_SUPP (BTRFS_HEADER_FLAG_WRITTEN |\
BTRFS_HEADER_FLAG_RELOC |\
BTRFS_SUPER_FLAG_ERROR |\
BTRFS_SUPER_FLAG_SEEDING |\
BTRFS_SUPER_FLAG_METADUMP |\
BTRFS_SUPER_FLAG_METADUMP_V2)
static const struct extent_io_ops btree_extent_io_ops;
static void end_workqueue_fn(struct btrfs_work *work);
static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
struct btrfs_fs_info *fs_info);
static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root);
static int btrfs_destroy_marked_extents(struct btrfs_fs_info *fs_info,
struct extent_io_tree *dirty_pages,
int mark);
static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info,
struct extent_io_tree *pinned_extents);
static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info);
static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info);
/*
* btrfs_end_io_wq structs are used to do processing in task context when an IO
* is complete. This is used during reads to verify checksums, and it is used
* by writes to insert metadata for new file extents after IO is complete.
*/
struct btrfs_end_io_wq {
struct bio *bio;
bio_end_io_t *end_io;
void *private;
struct btrfs_fs_info *info;
blk_status_t status;
enum btrfs_wq_endio_type metadata;
struct btrfs_work work;
};
static struct kmem_cache *btrfs_end_io_wq_cache;
int __init btrfs_end_io_wq_init(void)
{
btrfs_end_io_wq_cache = kmem_cache_create("btrfs_end_io_wq",
sizeof(struct btrfs_end_io_wq),
0,
SLAB_MEM_SPREAD,
NULL);
if (!btrfs_end_io_wq_cache)
return -ENOMEM;
return 0;
}
void __cold btrfs_end_io_wq_exit(void)
{
kmem_cache_destroy(btrfs_end_io_wq_cache);
}
/*
* async submit bios are used to offload expensive checksumming
* onto the worker threads. They checksum file and metadata bios
* just before they are sent down the IO stack.
*/
struct async_submit_bio {
void *private_data;
struct bio *bio;
extent_submit_bio_start_t *submit_bio_start;
int mirror_num;
/*
* bio_offset is optional, can be used if the pages in the bio
* can't tell us where in the file the bio should go
*/
u64 bio_offset;
struct btrfs_work work;
blk_status_t status;
};
/*
* Lockdep class keys for extent_buffer->lock's in this root. For a given
* eb, the lockdep key is determined by the btrfs_root it belongs to and
* the level the eb occupies in the tree.
*
* Different roots are used for different purposes and may nest inside each
* other and they require separate keysets. As lockdep keys should be
* static, assign keysets according to the purpose of the root as indicated
* by btrfs_root->root_key.objectid. This ensures that all special purpose
* roots have separate keysets.
*
* Lock-nesting across peer nodes is always done with the immediate parent
* node locked thus preventing deadlock. As lockdep doesn't know this, use
* subclass to avoid triggering lockdep warning in such cases.
*
* The key is set by the readpage_end_io_hook after the buffer has passed
* csum validation but before the pages are unlocked. It is also set by
* btrfs_init_new_buffer on freshly allocated blocks.
*
* We also add a check to make sure the highest level of the tree is the
* same as our lockdep setup here. If BTRFS_MAX_LEVEL changes, this code
* needs update as well.
*/
#ifdef CONFIG_DEBUG_LOCK_ALLOC
# if BTRFS_MAX_LEVEL != 8
# error
# endif
static struct btrfs_lockdep_keyset {
u64 id; /* root objectid */
const char *name_stem; /* lock name stem */
char names[BTRFS_MAX_LEVEL + 1][20];
struct lock_class_key keys[BTRFS_MAX_LEVEL + 1];
} btrfs_lockdep_keysets[] = {
{ .id = BTRFS_ROOT_TREE_OBJECTID, .name_stem = "root" },
{ .id = BTRFS_EXTENT_TREE_OBJECTID, .name_stem = "extent" },
{ .id = BTRFS_CHUNK_TREE_OBJECTID, .name_stem = "chunk" },
{ .id = BTRFS_DEV_TREE_OBJECTID, .name_stem = "dev" },
{ .id = BTRFS_FS_TREE_OBJECTID, .name_stem = "fs" },
{ .id = BTRFS_CSUM_TREE_OBJECTID, .name_stem = "csum" },
{ .id = BTRFS_QUOTA_TREE_OBJECTID, .name_stem = "quota" },
{ .id = BTRFS_TREE_LOG_OBJECTID, .name_stem = "log" },
{ .id = BTRFS_TREE_RELOC_OBJECTID, .name_stem = "treloc" },
{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc" },
{ .id = BTRFS_UUID_TREE_OBJECTID, .name_stem = "uuid" },
{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID, .name_stem = "free-space" },
{ .id = 0, .name_stem = "tree" },
};
void __init btrfs_init_lockdep(void)
{
int i, j;
/* initialize lockdep class names */
for (i = 0; i < ARRAY_SIZE(btrfs_lockdep_keysets); i++) {
struct btrfs_lockdep_keyset *ks = &btrfs_lockdep_keysets[i];
for (j = 0; j < ARRAY_SIZE(ks->names); j++)
snprintf(ks->names[j], sizeof(ks->names[j]),
"btrfs-%s-%02d", ks->name_stem, j);
}
}
void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
int level)
{
struct btrfs_lockdep_keyset *ks;
BUG_ON(level >= ARRAY_SIZE(ks->keys));
/* find the matching keyset, id 0 is the default entry */
for (ks = btrfs_lockdep_keysets; ks->id; ks++)
if (ks->id == objectid)
break;
lockdep_set_class_and_name(&eb->lock,
&ks->keys[level], ks->names[level]);
}
#endif
/*
* extents on the btree inode are pretty simple, there's one extent
* that covers the entire device
*/
struct extent_map *btree_get_extent(struct btrfs_inode *inode,
struct page *page, size_t pg_offset, u64 start, u64 len,
int create)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
struct extent_map_tree *em_tree = &inode->extent_tree;
struct extent_map *em;
int ret;
read_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, start, len);
if (em) {
em->bdev = fs_info->fs_devices->latest_bdev;
read_unlock(&em_tree->lock);
goto out;
}
read_unlock(&em_tree->lock);
em = alloc_extent_map();
if (!em) {
em = ERR_PTR(-ENOMEM);
goto out;
}
em->start = 0;
em->len = (u64)-1;
em->block_len = (u64)-1;
em->block_start = 0;
em->bdev = fs_info->fs_devices->latest_bdev;
write_lock(&em_tree->lock);
ret = add_extent_mapping(em_tree, em, 0);
if (ret == -EEXIST) {
free_extent_map(em);
em = lookup_extent_mapping(em_tree, start, len);
if (!em)
em = ERR_PTR(-EIO);
} else if (ret) {
free_extent_map(em);
em = ERR_PTR(ret);
}
write_unlock(&em_tree->lock);
out:
return em;
}
u32 btrfs_csum_data(const char *data, u32 seed, size_t len)
{
return crc32c(seed, data, len);
}
void btrfs_csum_final(u32 crc, u8 *result)
{
put_unaligned_le32(~crc, result);
}
/*
* compute the csum for a btree block, and either verify it or write it
* into the csum field of the block.
*/
static int csum_tree_block(struct btrfs_fs_info *fs_info,
struct extent_buffer *buf,
int verify)
{
u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
char result[BTRFS_CSUM_SIZE];
unsigned long len;
unsigned long cur_len;
unsigned long offset = BTRFS_CSUM_SIZE;
char *kaddr;
unsigned long map_start;
unsigned long map_len;
int err;
u32 crc = ~(u32)0;
len = buf->len - offset;
while (len > 0) {
/*
* Note: we don't need to check for the err == 1 case here, as
* with the given combination of 'start = BTRFS_CSUM_SIZE (32)'
* and 'min_len = 32' and the currently implemented mapping
* algorithm we cannot cross a page boundary.
*/
err = map_private_extent_buffer(buf, offset, 32,
&kaddr, &map_start, &map_len);
if (err)
return err;
cur_len = min(len, map_len - (offset - map_start));
crc = btrfs_csum_data(kaddr + offset - map_start,
crc, cur_len);
len -= cur_len;
offset += cur_len;
}
memset(result, 0, BTRFS_CSUM_SIZE);
btrfs_csum_final(crc, result);
if (verify) {
if (memcmp_extent_buffer(buf, result, 0, csum_size)) {
u32 val;
u32 found = 0;
memcpy(&found, result, csum_size);
read_extent_buffer(buf, &val, 0, csum_size);
btrfs_warn_rl(fs_info,
"%s checksum verify failed on %llu wanted %X found %X level %d",
fs_info->sb->s_id, buf->start,
val, found, btrfs_header_level(buf));
return -EUCLEAN;
}
} else {
write_extent_buffer(buf, result, 0, csum_size);
}
return 0;
}
/*
* we can't consider a given block up to date unless the transid of the
* block matches the transid in the parent node's pointer. This is how we
* detect blocks that either didn't get written at all or got written
* in the wrong place.
*/
static int verify_parent_transid(struct extent_io_tree *io_tree,
struct extent_buffer *eb, u64 parent_transid,
int atomic)
{
struct extent_state *cached_state = NULL;
int ret;
bool need_lock = (current->journal_info == BTRFS_SEND_TRANS_STUB);
if (!parent_transid || btrfs_header_generation(eb) == parent_transid)
return 0;
if (atomic)
return -EAGAIN;
if (need_lock) {
btrfs_tree_read_lock(eb);
btrfs_set_lock_blocking_read(eb);
}
lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1,
&cached_state);
if (extent_buffer_uptodate(eb) &&
btrfs_header_generation(eb) == parent_transid) {
ret = 0;
goto out;
}
btrfs_err_rl(eb->fs_info,
"parent transid verify failed on %llu wanted %llu found %llu",
eb->start,
parent_transid, btrfs_header_generation(eb));
ret = 1;
/*
* Things reading via commit roots that don't have normal protection,
* like send, can have a really old block in cache that may point at a
* block that has been freed and re-allocated. So don't clear uptodate
* if we find an eb that is under IO (dirty/writeback) because we could
* end up reading in the stale data and then writing it back out and
* making everybody very sad.
*/
if (!extent_buffer_under_io(eb))
clear_extent_buffer_uptodate(eb);
out:
unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1,
&cached_state);
if (need_lock)
btrfs_tree_read_unlock_blocking(eb);
return ret;
}
/*
* Return 0 if the superblock checksum type matches the checksum value of that
* algorithm. Pass the raw disk superblock data.
*/
static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info,
char *raw_disk_sb)
{
struct btrfs_super_block *disk_sb =
(struct btrfs_super_block *)raw_disk_sb;
u16 csum_type = btrfs_super_csum_type(disk_sb);
int ret = 0;
if (csum_type == BTRFS_CSUM_TYPE_CRC32) {
u32 crc = ~(u32)0;
char result[sizeof(crc)];
/*
* The super_block structure does not span the whole
* BTRFS_SUPER_INFO_SIZE range, we expect that the unused space
* is filled with zeros and is included in the checksum.
*/
crc = btrfs_csum_data(raw_disk_sb + BTRFS_CSUM_SIZE,
crc, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE);
btrfs_csum_final(crc, result);
if (memcmp(raw_disk_sb, result, sizeof(result)))
ret = 1;
}
if (csum_type >= ARRAY_SIZE(btrfs_csum_sizes)) {
btrfs_err(fs_info, "unsupported checksum algorithm %u",
csum_type);
ret = 1;
}
return ret;
}
static int verify_level_key(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb, int level,
struct btrfs_key *first_key, u64 parent_transid)
{
int found_level;
struct btrfs_key found_key;
int ret;
found_level = btrfs_header_level(eb);
if (found_level != level) {
#ifdef CONFIG_BTRFS_DEBUG
WARN_ON(1);
btrfs_err(fs_info,
"tree level mismatch detected, bytenr=%llu level expected=%u has=%u",
eb->start, level, found_level);
#endif
return -EIO;
}
if (!first_key)
return 0;
/*
* For live tree block (new tree blocks in current transaction),
* we need proper lock context to avoid race, which is impossible here.
* So we only checks tree blocks which is read from disk, whose
* generation <= fs_info->last_trans_committed.
*/
if (btrfs_header_generation(eb) > fs_info->last_trans_committed)
return 0;
if (found_level)
btrfs_node_key_to_cpu(eb, &found_key, 0);
else
btrfs_item_key_to_cpu(eb, &found_key, 0);
ret = btrfs_comp_cpu_keys(first_key, &found_key);
#ifdef CONFIG_BTRFS_DEBUG
if (ret) {
WARN_ON(1);
btrfs_err(fs_info,
"tree first key mismatch detected, bytenr=%llu parent_transid=%llu key expected=(%llu,%u,%llu) has=(%llu,%u,%llu)",
eb->start, parent_transid, first_key->objectid,
first_key->type, first_key->offset,
found_key.objectid, found_key.type,
found_key.offset);
}
#endif
return ret;
}
/*
* helper to read a given tree block, doing retries as required when
* the checksums don't match and we have alternate mirrors to try.
*
* @parent_transid: expected transid, skip check if 0
* @level: expected level, mandatory check
* @first_key: expected key of first slot, skip check if NULL
*/
static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb,
u64 parent_transid, int level,
struct btrfs_key *first_key)
{
struct extent_io_tree *io_tree;
int failed = 0;
int ret;
int num_copies = 0;
int mirror_num = 0;
int failed_mirror = 0;
io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
while (1) {
clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
ret = read_extent_buffer_pages(io_tree, eb, WAIT_COMPLETE,
mirror_num);
if (!ret) {
if (verify_parent_transid(io_tree, eb,
parent_transid, 0))
ret = -EIO;
else if (verify_level_key(fs_info, eb, level,
first_key, parent_transid))
ret = -EUCLEAN;
else
break;
}
num_copies = btrfs_num_copies(fs_info,
eb->start, eb->len);
if (num_copies == 1)
break;
if (!failed_mirror) {
failed = 1;
failed_mirror = eb->read_mirror;
}
mirror_num++;
if (mirror_num == failed_mirror)
mirror_num++;
if (mirror_num > num_copies)
break;
}
if (failed && !ret && failed_mirror)
repair_eb_io_failure(fs_info, eb, failed_mirror);
return ret;
}
/*
* checksum a dirty tree block before IO. This has extra checks to make sure
* we only fill in the checksum field in the first page of a multi-page block
*/
static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page)
{
u64 start = page_offset(page);
u64 found_start;
struct extent_buffer *eb;
eb = (struct extent_buffer *)page->private;
if (page != eb->pages[0])
return 0;
found_start = btrfs_header_bytenr(eb);
/*
* Please do not consolidate these warnings into a single if.
* It is useful to know what went wrong.
*/
if (WARN_ON(found_start != start))
return -EUCLEAN;
if (WARN_ON(!PageUptodate(page)))
return -EUCLEAN;
ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid,
btrfs_header_fsid(), BTRFS_FSID_SIZE) == 0);
return csum_tree_block(fs_info, eb, 0);
}
static int check_tree_block_fsid(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb)
{
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
u8 fsid[BTRFS_FSID_SIZE];
int ret = 1;
read_extent_buffer(eb, fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE);
while (fs_devices) {
u8 *metadata_uuid;
/*
* Checking the incompat flag is only valid for the current
* fs. For seed devices it's forbidden to have their uuid
* changed so reading ->fsid in this case is fine
*/
if (fs_devices == fs_info->fs_devices &&
btrfs_fs_incompat(fs_info, METADATA_UUID))
metadata_uuid = fs_devices->metadata_uuid;
else
metadata_uuid = fs_devices->fsid;
if (!memcmp(fsid, metadata_uuid, BTRFS_FSID_SIZE)) {
ret = 0;
break;
}
fs_devices = fs_devices->seed;
}
return ret;
}
static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
u64 phy_offset, struct page *page,
u64 start, u64 end, int mirror)
{
u64 found_start;
int found_level;
struct extent_buffer *eb;
struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
struct btrfs_fs_info *fs_info = root->fs_info;
int ret = 0;
int reads_done;
if (!page->private)
goto out;
eb = (struct extent_buffer *)page->private;
/* the pending IO might have been the only thing that kept this buffer
* in memory. Make sure we have a ref for all this other checks
*/
extent_buffer_get(eb);
reads_done = atomic_dec_and_test(&eb->io_pages);
if (!reads_done)
goto err;
eb->read_mirror = mirror;
if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) {
ret = -EIO;
goto err;
}
found_start = btrfs_header_bytenr(eb);
if (found_start != eb->start) {
btrfs_err_rl(fs_info, "bad tree block start, want %llu have %llu",
eb->start, found_start);
ret = -EIO;
goto err;
}
if (check_tree_block_fsid(fs_info, eb)) {
btrfs_err_rl(fs_info, "bad fsid on block %llu",
eb->start);
ret = -EIO;
goto err;
}
found_level = btrfs_header_level(eb);
if (found_level >= BTRFS_MAX_LEVEL) {
btrfs_err(fs_info, "bad tree block level %d on %llu",
(int)btrfs_header_level(eb), eb->start);
ret = -EIO;
goto err;
}
btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb),
eb, found_level);
ret = csum_tree_block(fs_info, eb, 1);
if (ret)
goto err;
/*
* If this is a leaf block and it is corrupt, set the corrupt bit so
* that we don't try and read the other copies of this block, just
* return -EIO.
*/
if (found_level == 0 && btrfs_check_leaf_full(fs_info, eb)) {
set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
ret = -EIO;
}
if (found_level > 0 && btrfs_check_node(fs_info, eb))
ret = -EIO;
if (!ret)
set_extent_buffer_uptodate(eb);
err:
if (reads_done &&
test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
btree_readahead_hook(eb, ret);
if (ret) {
/*
* our io error hook is going to dec the io pages
* again, we have to make sure it has something
* to decrement
*/
atomic_inc(&eb->io_pages);
clear_extent_buffer_uptodate(eb);
}
free_extent_buffer(eb);
out:
return ret;
}
static void end_workqueue_bio(struct bio *bio)
{
struct btrfs_end_io_wq *end_io_wq = bio->bi_private;
struct btrfs_fs_info *fs_info;
struct btrfs_workqueue *wq;
btrfs_work_func_t func;
fs_info = end_io_wq->info;
end_io_wq->status = bio->bi_status;
if (bio_op(bio) == REQ_OP_WRITE) {
if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) {
wq = fs_info->endio_meta_write_workers;
func = btrfs_endio_meta_write_helper;
} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) {
wq = fs_info->endio_freespace_worker;
func = btrfs_freespace_write_helper;
} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
wq = fs_info->endio_raid56_workers;
func = btrfs_endio_raid56_helper;
} else {
wq = fs_info->endio_write_workers;
func = btrfs_endio_write_helper;
}
} else {
if (unlikely(end_io_wq->metadata ==
BTRFS_WQ_ENDIO_DIO_REPAIR)) {
wq = fs_info->endio_repair_workers;
func = btrfs_endio_repair_helper;
} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
wq = fs_info->endio_raid56_workers;
func = btrfs_endio_raid56_helper;
} else if (end_io_wq->metadata) {
wq = fs_info->endio_meta_workers;
func = btrfs_endio_meta_helper;
} else {
wq = fs_info->endio_workers;
func = btrfs_endio_helper;
}
}
btrfs_init_work(&end_io_wq->work, func, end_workqueue_fn, NULL, NULL);
btrfs_queue_work(wq, &end_io_wq->work);
}
blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
enum btrfs_wq_endio_type metadata)
{
struct btrfs_end_io_wq *end_io_wq;
end_io_wq = kmem_cache_alloc(btrfs_end_io_wq_cache, GFP_NOFS);
if (!end_io_wq)
return BLK_STS_RESOURCE;
end_io_wq->private = bio->bi_private;
end_io_wq->end_io = bio->bi_end_io;
end_io_wq->info = info;
end_io_wq->status = 0;
end_io_wq->bio = bio;
end_io_wq->metadata = metadata;
bio->bi_private = end_io_wq;
bio->bi_end_io = end_workqueue_bio;
return 0;
}
static void run_one_async_start(struct btrfs_work *work)
{
struct async_submit_bio *async;
blk_status_t ret;
async = container_of(work, struct async_submit_bio, work);
ret = async->submit_bio_start(async->private_data, async->bio,
async->bio_offset);
if (ret)
async->status = ret;
}
/*
* In order to insert checksums into the metadata in large chunks, we wait
* until bio submission time. All the pages in the bio are checksummed and
* sums are attached onto the ordered extent record.
*
* At IO completion time the csums attached on the ordered extent record are
* inserted into the tree.
*/
static void run_one_async_done(struct btrfs_work *work)
{
struct async_submit_bio *async;
struct inode *inode;
blk_status_t ret;
async = container_of(work, struct async_submit_bio, work);
inode = async->private_data;
/* If an error occurred we just want to clean up the bio and move on */
if (async->status) {
async->bio->bi_status = async->status;
bio_endio(async->bio);
return;
}
ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio,
async->mirror_num, 1);
if (ret) {
async->bio->bi_status = ret;
bio_endio(async->bio);
}
}
static void run_one_async_free(struct btrfs_work *work)
{
struct async_submit_bio *async;
async = container_of(work, struct async_submit_bio, work);
kfree(async);
}
blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
int mirror_num, unsigned long bio_flags,
u64 bio_offset, void *private_data,
extent_submit_bio_start_t *submit_bio_start)
{
struct async_submit_bio *async;
async = kmalloc(sizeof(*async), GFP_NOFS);
if (!async)
return BLK_STS_RESOURCE;
async->private_data = private_data;
async->bio = bio;
async->mirror_num = mirror_num;
async->submit_bio_start = submit_bio_start;
btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start,
run_one_async_done, run_one_async_free);
async->bio_offset = bio_offset;
async->status = 0;
if (op_is_sync(bio->bi_opf))
btrfs_set_work_high_priority(&async->work);
btrfs_queue_work(fs_info->workers, &async->work);
return 0;
}
static blk_status_t btree_csum_one_bio(struct bio *bio)
{
struct bio_vec *bvec;
struct btrfs_root *root;
int i, ret = 0;
struct bvec_iter_all iter_all;
ASSERT(!bio_flagged(bio, BIO_CLONED));
bio_for_each_segment_all(bvec, bio, i, iter_all) {
root = BTRFS_I(bvec->bv_page->mapping->host)->root;
ret = csum_dirty_buffer(root->fs_info, bvec->bv_page);
if (ret)
break;
}
return errno_to_blk_status(ret);
}
static blk_status_t btree_submit_bio_start(void *private_data, struct bio *bio,
u64 bio_offset)
{
/*
* when we're called for a write, we're already in the async
* submission context. Just jump into btrfs_map_bio
*/
return btree_csum_one_bio(bio);
}
static int check_async_write(struct btrfs_inode *bi)
{
if (atomic_read(&bi->sync_writers))
return 0;
#ifdef CONFIG_X86
if (static_cpu_has(X86_FEATURE_XMM4_2))
return 0;
#endif
return 1;
}
static blk_status_t btree_submit_bio_hook(void *private_data, struct bio *bio,
int mirror_num, unsigned long bio_flags,
u64 bio_offset)
{
struct inode *inode = private_data;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
int async = check_async_write(BTRFS_I(inode));
blk_status_t ret;
if (bio_op(bio) != REQ_OP_WRITE) {
/*
* called for a read, do the setup so that checksum validation
* can happen in the async kernel threads
*/
ret = btrfs_bio_wq_end_io(fs_info, bio,
BTRFS_WQ_ENDIO_METADATA);
if (ret)
goto out_w_error;
ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
} else if (!async) {
ret = btree_csum_one_bio(bio);
if (ret)
goto out_w_error;
ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
} else {
/*
* kthread helpers are used to submit writes so that
* checksumming can happen in parallel across all CPUs
*/
ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, 0,
bio_offset, private_data,
btree_submit_bio_start);
}
if (ret)
goto out_w_error;
return 0;
out_w_error:
bio->bi_status = ret;
bio_endio(bio);
return ret;
}
#ifdef CONFIG_MIGRATION
static int btree_migratepage(struct address_space *mapping,
struct page *newpage, struct page *page,
enum migrate_mode mode)
{
/*
* we can't safely write a btree page from here,
* we haven't done the locking hook
*/
if (PageDirty(page))
return -EAGAIN;
/*
* Buffers may be managed in a filesystem specific way.
* We must have no buffers or drop them.
*/
if (page_has_private(page) &&
!try_to_release_page(page, GFP_KERNEL))
return -EAGAIN;
return migrate_page(mapping, newpage, page, mode);
}
#endif
static int btree_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct btrfs_fs_info *fs_info;
int ret;
if (wbc->sync_mode == WB_SYNC_NONE) {
if (wbc->for_kupdate)
return 0;
fs_info = BTRFS_I(mapping->host)->root->fs_info;
/* this is a bit racy, but that's ok */
ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes,
BTRFS_DIRTY_METADATA_THRESH,
fs_info->dirty_metadata_batch);
if (ret < 0)
return 0;
}
return btree_write_cache_pages(mapping, wbc);
}
static int btree_readpage(struct file *file, struct page *page)
{
struct extent_io_tree *tree;
tree = &BTRFS_I(page->mapping->host)->io_tree;
return extent_read_full_page(tree, page, btree_get_extent, 0);
}
static int btree_releasepage(struct page *page, gfp_t gfp_flags)
{
if (PageWriteback(page) || PageDirty(page))
return 0;
return try_release_extent_buffer(page);
}
static void btree_invalidatepage(struct page *page, unsigned int offset,
unsigned int length)
{
struct extent_io_tree *tree;
tree = &BTRFS_I(page->mapping->host)->io_tree;
extent_invalidatepage(tree, page, offset);
btree_releasepage(page, GFP_NOFS);
if (PagePrivate(page)) {
btrfs_warn(BTRFS_I(page->mapping->host)->root->fs_info,
"page private not zero on page %llu",
(unsigned long long)page_offset(page));
ClearPagePrivate(page);
set_page_private(page, 0);
put_page(page);
}
}
static int btree_set_page_dirty(struct page *page)
{
#ifdef DEBUG
struct extent_buffer *eb;
BUG_ON(!PagePrivate(page));
eb = (struct extent_buffer *)page->private;
BUG_ON(!eb);
BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
BUG_ON(!atomic_read(&eb->refs));
btrfs_assert_tree_locked(eb);
#endif
return __set_page_dirty_nobuffers(page);
}
static const struct address_space_operations btree_aops = {
.readpage = btree_readpage,
.writepages = btree_writepages,
.releasepage = btree_releasepage,
.invalidatepage = btree_invalidatepage,
#ifdef CONFIG_MIGRATION
.migratepage = btree_migratepage,
#endif
.set_page_dirty = btree_set_page_dirty,
};
void readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr)
{
struct extent_buffer *buf = NULL;
struct inode *btree_inode = fs_info->btree_inode;
buf = btrfs_find_create_tree_block(fs_info, bytenr);
if (IS_ERR(buf))
return;
read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
buf, WAIT_NONE, 0);
free_extent_buffer(buf);
}
int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr,
int mirror_num, struct extent_buffer **eb)
{
struct extent_buffer *buf = NULL;
struct inode *btree_inode = fs_info->btree_inode;
struct extent_io_tree *io_tree = &BTRFS_I(btree_inode)->io_tree;
int ret;
buf = btrfs_find_create_tree_block(fs_info, bytenr);
if (IS_ERR(buf))
return 0;
set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags);
ret = read_extent_buffer_pages(io_tree, buf, WAIT_PAGE_LOCK,
mirror_num);
if (ret) {
free_extent_buffer(buf);
return ret;
}
if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags)) {
free_extent_buffer(buf);
return -EIO;
} else if (extent_buffer_uptodate(buf)) {
*eb = buf;
} else {
free_extent_buffer(buf);
}
return 0;
}
struct extent_buffer *btrfs_find_create_tree_block(
struct btrfs_fs_info *fs_info,
u64 bytenr)
{
if (btrfs_is_testing(fs_info))
return alloc_test_extent_buffer(fs_info, bytenr);
return alloc_extent_buffer(fs_info, bytenr);
}
int btrfs_write_tree_block(struct extent_buffer *buf)
{
return filemap_fdatawrite_range(buf->pages[0]->mapping, buf->start,
buf->start + buf->len - 1);
}
void btrfs_wait_tree_block_writeback(struct extent_buffer *buf)
{
filemap_fdatawait_range(buf->pages[0]->mapping,
buf->start, buf->start + buf->len - 1);
}
/*
* Read tree block at logical address @bytenr and do variant basic but critical
* verification.
*
* @parent_transid: expected transid of this tree block, skip check if 0
* @level: expected level, mandatory check
* @first_key: expected key in slot 0, skip check if NULL
*/
struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
u64 parent_transid, int level,
struct btrfs_key *first_key)
{
struct extent_buffer *buf = NULL;
int ret;
buf = btrfs_find_create_tree_block(fs_info, bytenr);
if (IS_ERR(buf))
return buf;
ret = btree_read_extent_buffer_pages(fs_info, buf, parent_transid,
level, first_key);
if (ret) {
free_extent_buffer(buf);
return ERR_PTR(ret);
}
return buf;
}
void clean_tree_block(struct btrfs_fs_info *fs_info,
struct extent_buffer *buf)
{
if (btrfs_header_generation(buf) ==
fs_info->running_transaction->transid) {
btrfs_assert_tree_locked(buf);
if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) {
percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
-buf->len,
fs_info->dirty_metadata_batch);
/* ugh, clear_extent_buffer_dirty needs to lock the page */
btrfs_set_lock_blocking_write(buf);
clear_extent_buffer_dirty(buf);
}
}
}
static struct btrfs_subvolume_writers *btrfs_alloc_subvolume_writers(void)
{
struct btrfs_subvolume_writers *writers;
int ret;
writers = kmalloc(sizeof(*writers), GFP_NOFS);
if (!writers)
return ERR_PTR(-ENOMEM);
ret = percpu_counter_init(&writers->counter, 0, GFP_NOFS);
if (ret < 0) {
kfree(writers);
return ERR_PTR(ret);
}
init_waitqueue_head(&writers->wait);
return writers;
}
static void
btrfs_free_subvolume_writers(struct btrfs_subvolume_writers *writers)
{
percpu_counter_destroy(&writers->counter);
kfree(writers);
}
static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
u64 objectid)
{
bool dummy = test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state);
root->node = NULL;
root->commit_root = NULL;
root->state = 0;
root->orphan_cleanup_state = 0;
root->last_trans = 0;
root->highest_objectid = 0;
root->nr_delalloc_inodes = 0;
root->nr_ordered_extents = 0;
root->inode_tree = RB_ROOT;
INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
root->block_rsv = NULL;
INIT_LIST_HEAD(&root->dirty_list);
INIT_LIST_HEAD(&root->root_list);
INIT_LIST_HEAD(&root->delalloc_inodes);
INIT_LIST_HEAD(&root->delalloc_root);
INIT_LIST_HEAD(&root->ordered_extents);
INIT_LIST_HEAD(&root->ordered_root);
INIT_LIST_HEAD(&root->reloc_dirty_list);
INIT_LIST_HEAD(&root->logged_list[0]);
INIT_LIST_HEAD(&root->logged_list[1]);
spin_lock_init(&root->inode_lock);
spin_lock_init(&root->delalloc_lock);
spin_lock_init(&root->ordered_extent_lock);
spin_lock_init(&root->accounting_lock);
spin_lock_init(&root->log_extents_lock[0]);
spin_lock_init(&root->log_extents_lock[1]);
spin_lock_init(&root->qgroup_meta_rsv_lock);
mutex_init(&root->objectid_mutex);
mutex_init(&root->log_mutex);
mutex_init(&root->ordered_extent_mutex);
mutex_init(&root->delalloc_mutex);
init_waitqueue_head(&root->log_writer_wait);
init_waitqueue_head(&root->log_commit_wait[0]);
init_waitqueue_head(&root->log_commit_wait[1]);
INIT_LIST_HEAD(&root->log_ctxs[0]);
INIT_LIST_HEAD(&root->log_ctxs[1]);
atomic_set(&root->log_commit[0], 0);
atomic_set(&root->log_commit[1], 0);
atomic_set(&root->log_writers, 0);
atomic_set(&root->log_batch, 0);
refcount_set(&root->refs, 1);
atomic_set(&root->will_be_snapshotted, 0);
atomic_set(&root->snapshot_force_cow, 0);
atomic_set(&root->nr_swapfiles, 0);
root->log_transid = 0;
root->log_transid_committed = -1;
root->last_log_commit = 0;
if (!dummy)
extent_io_tree_init(&root->dirty_log_pages, NULL);
memset(&root->root_key, 0, sizeof(root->root_key));
memset(&root->root_item, 0, sizeof(root->root_item));
memset(&root->defrag_progress, 0, sizeof(root->defrag_progress));
if (!dummy)
root->defrag_trans_start = fs_info->generation;
else
root->defrag_trans_start = 0;
root->root_key.objectid = objectid;
root->anon_dev = 0;
spin_lock_init(&root->root_item_lock);
btrfs_qgroup_init_swapped_blocks(&root->swapped_blocks);
}
static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info,
gfp_t flags)
{
struct btrfs_root *root = kzalloc(sizeof(*root), flags);
if (root)
root->fs_info = fs_info;
return root;
}
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
/* Should only be used by the testing infrastructure */
struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info)
{
struct btrfs_root *root;
if (!fs_info)
return ERR_PTR(-EINVAL);
root = btrfs_alloc_root(fs_info, GFP_KERNEL);
if (!root)
return ERR_PTR(-ENOMEM);
/* We don't use the stripesize in selftest, set it as sectorsize */
__setup_root(root, fs_info, BTRFS_ROOT_TREE_OBJECTID);
root->alloc_bytenr = 0;
return root;
}
#endif
struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
u64 objectid)
{
struct extent_buffer *leaf;
struct btrfs_root *tree_root = fs_info->tree_root;
struct btrfs_root *root;
struct btrfs_key key;
unsigned int nofs_flag;
int ret = 0;
uuid_le uuid = NULL_UUID_LE;
/*
* We're holding a transaction handle, so use a NOFS memory allocation
* context to avoid deadlock if reclaim happens.
*/
nofs_flag = memalloc_nofs_save();
root = btrfs_alloc_root(fs_info, GFP_KERNEL);
memalloc_nofs_restore(nofs_flag);
if (!root)
return ERR_PTR(-ENOMEM);
__setup_root(root, fs_info, objectid);
root->root_key.objectid = objectid;
root->root_key.type = BTRFS_ROOT_ITEM_KEY;
root->root_key.offset = 0;
leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0);
if (IS_ERR(leaf)) {
ret = PTR_ERR(leaf);
leaf = NULL;
goto fail;
}
root->node = leaf;
btrfs_mark_buffer_dirty(leaf);
root->commit_root = btrfs_root_node(root);
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
root->root_item.flags = 0;
root->root_item.byte_limit = 0;
btrfs_set_root_bytenr(&root->root_item, leaf->start);
btrfs_set_root_generation(&root->root_item, trans->transid);
btrfs_set_root_level(&root->root_item, 0);
btrfs_set_root_refs(&root->root_item, 1);
btrfs_set_root_used(&root->root_item, leaf->len);
btrfs_set_root_last_snapshot(&root->root_item, 0);
btrfs_set_root_dirid(&root->root_item, 0);
if (is_fstree(objectid))
uuid_le_gen(&uuid);
memcpy(root->root_item.uuid, uuid.b, BTRFS_UUID_SIZE);
root->root_item.drop_level = 0;
key.objectid = objectid;
key.type = BTRFS_ROOT_ITEM_KEY;
key.offset = 0;
ret = btrfs_insert_root(trans, tree_root, &key, &root->root_item);
if (ret)
goto fail;
btrfs_tree_unlock(leaf);
return root;
fail:
if (leaf) {
btrfs_tree_unlock(leaf);
free_extent_buffer(root->commit_root);
free_extent_buffer(leaf);
}
kfree(root);
return ERR_PTR(ret);
}
static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info)
{
struct btrfs_root *root;
struct extent_buffer *leaf;
root = btrfs_alloc_root(fs_info, GFP_NOFS);
if (!root)
return ERR_PTR(-ENOMEM);
__setup_root(root, fs_info, BTRFS_TREE_LOG_OBJECTID);
root->root_key.objectid = BTRFS_TREE_LOG_OBJECTID;
root->root_key.type = BTRFS_ROOT_ITEM_KEY;
root->root_key.offset = BTRFS_TREE_LOG_OBJECTID;
/*
* DON'T set REF_COWS for log trees
*
* log trees do not get reference counted because they go away
* before a real commit is actually done. They do store pointers
* to file data extents, and those reference counts still get
* updated (along with back refs to the log tree).
*/
leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID,
NULL, 0, 0, 0);
if (IS_ERR(leaf)) {
kfree(root);
return ERR_CAST(leaf);
}
root->node = leaf;
btrfs_mark_buffer_dirty(root->node);
btrfs_tree_unlock(root->node);
return root;
}
int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info)
{
struct btrfs_root *log_root;
log_root = alloc_log_tree(trans, fs_info);
if (IS_ERR(log_root))
return PTR_ERR(log_root);
WARN_ON(fs_info->log_root_tree);
fs_info->log_root_tree = log_root;
return 0;
}
int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_root *log_root;
struct btrfs_inode_item *inode_item;
log_root = alloc_log_tree(trans, fs_info);
if (IS_ERR(log_root))
return PTR_ERR(log_root);
log_root->last_trans = trans->transid;
log_root->root_key.offset = root->root_key.objectid;
inode_item = &log_root->root_item.inode;
btrfs_set_stack_inode_generation(inode_item, 1);
btrfs_set_stack_inode_size(inode_item, 3);
btrfs_set_stack_inode_nlink(inode_item, 1);
btrfs_set_stack_inode_nbytes(inode_item,
fs_info->nodesize);
btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);
btrfs_set_root_node(&log_root->root_item, log_root->node);
WARN_ON(root->log_root);
root->log_root = log_root;
root->log_transid = 0;
root->log_transid_committed = -1;
root->last_log_commit = 0;
return 0;
}
static struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
struct btrfs_key *key)
{
struct btrfs_root *root;
struct btrfs_fs_info *fs_info = tree_root->fs_info;
struct btrfs_path *path;
u64 generation;
int ret;
int level;
path = btrfs_alloc_path();
if (!path)
return ERR_PTR(-ENOMEM);
root = btrfs_alloc_root(fs_info, GFP_NOFS);
if (!root) {
ret = -ENOMEM;
goto alloc_fail;
}
__setup_root(root, fs_info, key->objectid);
ret = btrfs_find_root(tree_root, key, path,
&root->root_item, &root->root_key);
if (ret) {
if (ret > 0)
ret = -ENOENT;
goto find_fail;
}
generation = btrfs_root_generation(&root->root_item);
level = btrfs_root_level(&root->root_item);
root->node = read_tree_block(fs_info,
btrfs_root_bytenr(&root->root_item),
generation, level, NULL);
if (IS_ERR(root->node)) {
ret = PTR_ERR(root->node);
goto find_fail;
} else if (!btrfs_buffer_uptodate(root->node, generation, 0)) {
ret = -EIO;
free_extent_buffer(root->node);
goto find_fail;
}
root->commit_root = btrfs_root_node(root);
out:
btrfs_free_path(path);
return root;
find_fail:
kfree(root);
alloc_fail:
root = ERR_PTR(ret);
goto out;
}
struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root,
struct btrfs_key *location)
{
struct btrfs_root *root;
root = btrfs_read_tree_root(tree_root, location);
if (IS_ERR(root))
return root;
if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
set_bit(BTRFS_ROOT_REF_COWS, &root->state);
btrfs_check_and_init_root_item(&root->root_item);
}
return root;
}
int btrfs_init_fs_root(struct btrfs_root *root)
{
int ret;
struct btrfs_subvolume_writers *writers;
root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS);
root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned),
GFP_NOFS);
if (!root->free_ino_pinned || !root->free_ino_ctl) {
ret = -ENOMEM;
goto fail;
}
writers = btrfs_alloc_subvolume_writers();
if (IS_ERR(writers)) {
ret = PTR_ERR(writers);
goto fail;
}
root->subv_writers = writers;
btrfs_init_free_ino_ctl(root);
spin_lock_init(&root->ino_cache_lock);
init_waitqueue_head(&root->ino_cache_wait);
ret = get_anon_bdev(&root->anon_dev);
if (ret)
goto fail;
mutex_lock(&root->objectid_mutex);
ret = btrfs_find_highest_objectid(root,
&root->highest_objectid);
if (ret) {
mutex_unlock(&root->objectid_mutex);
goto fail;
}
ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
mutex_unlock(&root->objectid_mutex);
return 0;
fail:
/* The caller is responsible to call btrfs_free_fs_root */
return ret;
}
struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
u64 root_id)
{
struct btrfs_root *root;
spin_lock(&fs_info->fs_roots_radix_lock);
root = radix_tree_lookup(&fs_info->fs_roots_radix,
(unsigned long)root_id);
spin_unlock(&fs_info->fs_roots_radix_lock);
return root;
}
int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
struct btrfs_root *root)
{
int ret;
ret = radix_tree_preload(GFP_NOFS);
if (ret)
return ret;
spin_lock(&fs_info->fs_roots_radix_lock);
ret = radix_tree_insert(&fs_info->fs_roots_radix,
(unsigned long)root->root_key.objectid,
root);
if (ret == 0)
set_bit(BTRFS_ROOT_IN_RADIX, &root->state);
spin_unlock(&fs_info->fs_roots_radix_lock);
radix_tree_preload_end();
return ret;
}
struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
struct btrfs_key *location,
bool check_ref)
{
struct btrfs_root *root;
struct btrfs_path *path;
struct btrfs_key key;
int ret;
if (location->objectid == BTRFS_ROOT_TREE_OBJECTID)
return fs_info->tree_root;
if (location->objectid == BTRFS_EXTENT_TREE_OBJECTID)
return fs_info->extent_root;
if (location->objectid == BTRFS_CHUNK_TREE_OBJECTID)
return fs_info->chunk_root;
if (location->objectid == BTRFS_DEV_TREE_OBJECTID)
return fs_info->dev_root;
if (location->objectid == BTRFS_CSUM_TREE_OBJECTID)
return fs_info->csum_root;
if (location->objectid == BTRFS_QUOTA_TREE_OBJECTID)
return fs_info->quota_root ? fs_info->quota_root :
ERR_PTR(-ENOENT);
if (location->objectid == BTRFS_UUID_TREE_OBJECTID)
return fs_info->uuid_root ? fs_info->uuid_root :
ERR_PTR(-ENOENT);
if (location->objectid == BTRFS_FREE_SPACE_TREE_OBJECTID)
return fs_info->free_space_root ? fs_info->free_space_root :
ERR_PTR(-ENOENT);
again:
root = btrfs_lookup_fs_root(fs_info, location->objectid);
if (root) {
if (check_ref && btrfs_root_refs(&root->root_item) == 0)
return ERR_PTR(-ENOENT);
return root;
}
root = btrfs_read_fs_root(fs_info->tree_root, location);
if (IS_ERR(root))
return root;
if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
ret = -ENOENT;
goto fail;
}
ret = btrfs_init_fs_root(root);
if (ret)
goto fail;
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
goto fail;
}
key.objectid = BTRFS_ORPHAN_OBJECTID;
key.type = BTRFS_ORPHAN_ITEM_KEY;
key.offset = location->objectid;
ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
btrfs_free_path(path);
if (ret < 0)
goto fail;
if (ret == 0)
set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);
ret = btrfs_insert_fs_root(fs_info, root);
if (ret) {
if (ret == -EEXIST) {
btrfs_free_fs_root(root);
goto again;
}
goto fail;
}
return root;
fail:
btrfs_free_fs_root(root);
return ERR_PTR(ret);
}
static int btrfs_congested_fn(void *congested_data, int bdi_bits)
{
struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data;
int ret = 0;
struct btrfs_device *device;
struct backing_dev_info *bdi;
rcu_read_lock();
list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) {
if (!device->bdev)
continue;
bdi = device->bdev->bd_bdi;
if (bdi_congested(bdi, bdi_bits)) {
ret = 1;
break;
}
}
rcu_read_unlock();
return ret;
}
/*
* called by the kthread helper functions to finally call the bio end_io
* functions. This is where read checksum verification actually happens
*/
static void end_workqueue_fn(struct btrfs_work *work)
{
struct bio *bio;
struct btrfs_end_io_wq *end_io_wq;
end_io_wq = container_of(work, struct btrfs_end_io_wq, work);
bio = end_io_wq->bio;
bio->bi_status = end_io_wq->status;
bio->bi_private = end_io_wq->private;
bio->bi_end_io = end_io_wq->end_io;
kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
bio_endio(bio);
}
static int cleaner_kthread(void *arg)
{
struct btrfs_root *root = arg;
struct btrfs_fs_info *fs_info = root->fs_info;
int again;
while (1) {
again = 0;
set_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
/* Make the cleaner go to sleep early. */
if (btrfs_need_cleaner_sleep(fs_info))
goto sleep;
/*
* Do not do anything if we might cause open_ctree() to block
* before we have finished mounting the filesystem.
*/
if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags))
goto sleep;
if (!mutex_trylock(&fs_info->cleaner_mutex))
goto sleep;
/*
* Avoid the problem that we change the status of the fs
* during the above check and trylock.
*/
if (btrfs_need_cleaner_sleep(fs_info)) {
mutex_unlock(&fs_info->cleaner_mutex);
goto sleep;
}
btrfs_run_delayed_iputs(fs_info);
again = btrfs_clean_one_deleted_snapshot(root);
mutex_unlock(&fs_info->cleaner_mutex);
/*
* The defragger has dealt with the R/O remount and umount,
* needn't do anything special here.
*/
btrfs_run_defrag_inodes(fs_info);
/*
* Acquires fs_info->delete_unused_bgs_mutex to avoid racing
* with relocation (btrfs_relocate_chunk) and relocation
* acquires fs_info->cleaner_mutex (btrfs_relocate_block_group)
* after acquiring fs_info->delete_unused_bgs_mutex. So we
* can't hold, nor need to, fs_info->cleaner_mutex when deleting
* unused block groups.
*/
btrfs_delete_unused_bgs(fs_info);
sleep:
clear_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
if (kthread_should_park())
kthread_parkme();
if (kthread_should_stop())
return 0;
if (!again) {
set_current_state(TASK_INTERRUPTIBLE);
schedule();
__set_current_state(TASK_RUNNING);
}
}
}
static int transaction_kthread(void *arg)
{
struct btrfs_root *root = arg;
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_trans_handle *trans;
struct btrfs_transaction *cur;
u64 transid;
time64_t now;
unsigned long delay;
bool cannot_commit;
do {
cannot_commit = false;
delay = HZ * fs_info->commit_interval;
mutex_lock(&fs_info->transaction_kthread_mutex);
spin_lock(&fs_info->trans_lock);
cur = fs_info->running_transaction;
if (!cur) {
spin_unlock(&fs_info->trans_lock);
goto sleep;
}
now = ktime_get_seconds();
if (cur->state < TRANS_STATE_BLOCKED &&
!test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) &&
(now < cur->start_time ||
now - cur->start_time < fs_info->commit_interval)) {
spin_unlock(&fs_info->trans_lock);
delay = HZ * 5;
goto sleep;
}
transid = cur->transid;
spin_unlock(&fs_info->trans_lock);
/* If the file system is aborted, this will always fail. */
trans = btrfs_attach_transaction(root);
if (IS_ERR(trans)) {
if (PTR_ERR(trans) != -ENOENT)
cannot_commit = true;
goto sleep;
}
if (transid == trans->transid) {
btrfs_commit_transaction(trans);
} else {
btrfs_end_transaction(trans);
}
sleep:
wake_up_process(fs_info->cleaner_kthread);
mutex_unlock(&fs_info->transaction_kthread_mutex);
if (unlikely(test_bit(BTRFS_FS_STATE_ERROR,
&fs_info->fs_state)))
btrfs_cleanup_transaction(fs_info);
if (!kthread_should_stop() &&
(!btrfs_transaction_blocked(fs_info) ||
cannot_commit))
schedule_timeout_interruptible(delay);
} while (!kthread_should_stop());
return 0;
}
/*
* this will find the highest generation in the array of
* root backups. The index of the highest array is returned,
* or -1 if we can't find anything.
*
* We check to make sure the array is valid by comparing the
* generation of the latest root in the array with the generation
* in the super block. If they don't match we pitch it.
*/
static int find_newest_super_backup(struct btrfs_fs_info *info, u64 newest_gen)
{
u64 cur;
int newest_index = -1;
struct btrfs_root_backup *root_backup;
int i;
for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) {
root_backup = info->super_copy->super_roots + i;
cur = btrfs_backup_tree_root_gen(root_backup);
if (cur == newest_gen)
newest_index = i;
}
/* check to see if we actually wrapped around */
if (newest_index == BTRFS_NUM_BACKUP_ROOTS - 1) {
root_backup = info->super_copy->super_roots;
cur = btrfs_backup_tree_root_gen(root_backup);
if (cur == newest_gen)
newest_index = 0;
}
return newest_index;
}
/*
* find the oldest backup so we know where to store new entries
* in the backup array. This will set the backup_root_index
* field in the fs_info struct
*/
static void find_oldest_super_backup(struct btrfs_fs_info *info,
u64 newest_gen)
{
int newest_index = -1;
newest_index = find_newest_super_backup(info, newest_gen);
/* if there was garbage in there, just move along */
if (newest_index == -1) {
info->backup_root_index = 0;
} else {
info->backup_root_index = (newest_index + 1) % BTRFS_NUM_BACKUP_ROOTS;
}
}
/*
* copy all the root pointers into the super backup array.
* this will bump the backup pointer by one when it is
* done
*/
static void backup_super_roots(struct btrfs_fs_info *info)
{
int next_backup;
struct btrfs_root_backup *root_backup;
int last_backup;
next_backup = info->backup_root_index;
last_backup = (next_backup + BTRFS_NUM_BACKUP_ROOTS - 1) %
BTRFS_NUM_BACKUP_ROOTS;
/*
* just overwrite the last backup if we're at the same generation
* this happens only at umount
*/
root_backup = info->super_for_commit->super_roots + last_backup;
if (btrfs_backup_tree_root_gen(root_backup) ==
btrfs_header_generation(info->tree_root->node))
next_backup = last_backup;
root_backup = info->super_for_commit->super_roots + next_backup;
/*
* make sure all of our padding and empty slots get zero filled
* regardless of which ones we use today
*/
memset(root_backup, 0, sizeof(*root_backup));
info->backup_root_index = (next_backup + 1) % BTRFS_NUM_BACKUP_ROOTS;
btrfs_set_backup_tree_root(root_backup, info->tree_root->node->start);
btrfs_set_backup_tree_root_gen(root_backup,
btrfs_header_generation(info->tree_root->node));
btrfs_set_backup_tree_root_level(root_backup,
btrfs_header_level(info->tree_root->node));
btrfs_set_backup_chunk_root(root_backup, info->chunk_root->node->start);
btrfs_set_backup_chunk_root_gen(root_backup,
btrfs_header_generation(info->chunk_root->node));
btrfs_set_backup_chunk_root_level(root_backup,
btrfs_header_level(info->chunk_root->node));
btrfs_set_backup_extent_root(root_backup, info->extent_root->node->start);
btrfs_set_backup_extent_root_gen(root_backup,
btrfs_header_generation(info->extent_root->node));
btrfs_set_backup_extent_root_level(root_backup,
btrfs_header_level(info->extent_root->node));
/*
* we might commit during log recovery, which happens before we set
* the fs_root. Make sure it is valid before we fill it in.
*/
if (info->fs_root && info->fs_root->node) {
btrfs_set_backup_fs_root(root_backup,
info->fs_root->node->start);
btrfs_set_backup_fs_root_gen(root_backup,
btrfs_header_generation(info->fs_root->node));
btrfs_set_backup_fs_root_level(root_backup,
btrfs_header_level(info->fs_root->node));
}
btrfs_set_backup_dev_root(root_backup, info->dev_root->node->start);
btrfs_set_backup_dev_root_gen(root_backup,
btrfs_header_generation(info->dev_root->node));
btrfs_set_backup_dev_root_level(root_backup,
btrfs_header_level(info->dev_root->node));
btrfs_set_backup_csum_root(root_backup, info->csum_root->node->start);
btrfs_set_backup_csum_root_gen(root_backup,
btrfs_header_generation(info->csum_root->node));
btrfs_set_backup_csum_root_level(root_backup,
btrfs_header_level(info->csum_root->node));
btrfs_set_backup_total_bytes(root_backup,
btrfs_super_total_bytes(info->super_copy));
btrfs_set_backup_bytes_used(root_backup,
btrfs_super_bytes_used(info->super_copy));
btrfs_set_backup_num_devices(root_backup,
btrfs_super_num_devices(info->super_copy));
/*
* if we don't copy this out to the super_copy, it won't get remembered
* for the next commit
*/
memcpy(&info->super_copy->super_roots,
&info->super_for_commit->super_roots,
sizeof(*root_backup) * BTRFS_NUM_BACKUP_ROOTS);
}
/*
* this copies info out of the root backup array and back into
* the in-memory super block. It is meant to help iterate through
* the array, so you send it the number of backups you've already
* tried and the last backup index you used.
*
* this returns -1 when it has tried all the backups
*/
static noinline int next_root_backup(struct btrfs_fs_info *info,
struct btrfs_super_block *super,
int *num_backups_tried, int *backup_index)
{
struct btrfs_root_backup *root_backup;
int newest = *backup_index;
if (*num_backups_tried == 0) {
u64 gen = btrfs_super_generation(super);
newest = find_newest_super_backup(info, gen);
if (newest == -1)
return -1;
*backup_index = newest;
*num_backups_tried = 1;
} else if (*num_backups_tried == BTRFS_NUM_BACKUP_ROOTS) {
/* we've tried all the backups, all done */
return -1;
} else {
/* jump to the next oldest backup */
newest = (*backup_index + BTRFS_NUM_BACKUP_ROOTS - 1) %
BTRFS_NUM_BACKUP_ROOTS;
*backup_index = newest;
*num_backups_tried += 1;
}
root_backup = super->super_roots + newest;
btrfs_set_super_generation(super,
btrfs_backup_tree_root_gen(root_backup));
btrfs_set_super_root(super, btrfs_backup_tree_root(root_backup));
btrfs_set_super_root_level(super,
btrfs_backup_tree_root_level(root_backup));
btrfs_set_super_bytes_used(super, btrfs_backup_bytes_used(root_backup));
/*
* fixme: the total bytes and num_devices need to match or we should
* need a fsck
*/
btrfs_set_super_total_bytes(super, btrfs_backup_total_bytes(root_backup));
btrfs_set_super_num_devices(super, btrfs_backup_num_devices(root_backup));
return 0;
}
/* helper to cleanup workers */
static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
{
btrfs_destroy_workqueue(fs_info->fixup_workers);
btrfs_destroy_workqueue(fs_info->delalloc_workers);
btrfs_destroy_workqueue(fs_info->workers);
btrfs_destroy_workqueue(fs_info->endio_workers);
btrfs_destroy_workqueue(fs_info->endio_raid56_workers);
btrfs_destroy_workqueue(fs_info->endio_repair_workers);
btrfs_destroy_workqueue(fs_info->rmw_workers);
btrfs_destroy_workqueue(fs_info->endio_write_workers);
btrfs_destroy_workqueue(fs_info->endio_freespace_worker);
btrfs_destroy_workqueue(fs_info->submit_workers);
btrfs_destroy_workqueue(fs_info->delayed_workers);
btrfs_destroy_workqueue(fs_info->caching_workers);
btrfs_destroy_workqueue(fs_info->readahead_workers);
btrfs_destroy_workqueue(fs_info->flush_workers);
btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers);
btrfs_destroy_workqueue(fs_info->extent_workers);
/*
* Now that all other work queues are destroyed, we can safely destroy
* the queues used for metadata I/O, since tasks from those other work
* queues can do metadata I/O operations.
*/
btrfs_destroy_workqueue(fs_info->endio_meta_workers);
btrfs_destroy_workqueue(fs_info->endio_meta_write_workers);
}
static void free_root_extent_buffers(struct btrfs_root *root)
{
if (root) {
free_extent_buffer(root->node);
free_extent_buffer(root->commit_root);
root->node = NULL;
root->commit_root = NULL;
}
}
/* helper to cleanup tree roots */
static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
{
free_root_extent_buffers(info->tree_root);
free_root_extent_buffers(info->dev_root);
free_root_extent_buffers(info->extent_root);
free_root_extent_buffers(info->csum_root);
free_root_extent_buffers(info->quota_root);
free_root_extent_buffers(info->uuid_root);
if (chunk_root)
free_root_extent_buffers(info->chunk_root);
free_root_extent_buffers(info->free_space_root);
}
void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info)
{
int ret;
struct btrfs_root *gang[8];
int i;
while (!list_empty(&fs_info->dead_roots)) {
gang[0] = list_entry(fs_info->dead_roots.next,
struct btrfs_root, root_list);
list_del(&gang[0]->root_list);
if (test_bit(BTRFS_ROOT_IN_RADIX, &gang[0]->state)) {
btrfs_drop_and_free_fs_root(fs_info, gang[0]);
} else {
free_extent_buffer(gang[0]->node);
free_extent_buffer(gang[0]->commit_root);
btrfs_put_fs_root(gang[0]);
}
}
while (1) {
ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
(void **)gang, 0,
ARRAY_SIZE(gang));
if (!ret)
break;
for (i = 0; i < ret; i++)
btrfs_drop_and_free_fs_root(fs_info, gang[i]);
}
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
btrfs_free_log_root_tree(NULL, fs_info);
btrfs_destroy_pinned_extent(fs_info, fs_info->pinned_extents);
}
}
static void btrfs_init_scrub(struct btrfs_fs_info *fs_info)
{
mutex_init(&fs_info->scrub_lock);
atomic_set(&fs_info->scrubs_running, 0);
atomic_set(&fs_info->scrub_pause_req, 0);
atomic_set(&fs_info->scrubs_paused, 0);
atomic_set(&fs_info->scrub_cancel_req, 0);
init_waitqueue_head(&fs_info->scrub_pause_wait);
refcount_set(&fs_info->scrub_workers_refcnt, 0);
}
static void btrfs_init_balance(struct btrfs_fs_info *fs_info)
{
spin_lock_init(&fs_info->balance_lock);
mutex_init(&fs_info->balance_mutex);
atomic_set(&fs_info->balance_pause_req, 0);
atomic_set(&fs_info->balance_cancel_req, 0);
fs_info->balance_ctl = NULL;
init_waitqueue_head(&fs_info->balance_wait_q);
}
static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info)
{
struct inode *inode = fs_info->btree_inode;
inode->i_ino = BTRFS_BTREE_INODE_OBJECTID;
set_nlink(inode, 1);
/*
* we set the i_size on the btree inode to the max possible int.
* the real end of the address space is determined by all of
* the devices in the system
*/
inode->i_size = OFFSET_MAX;
inode->i_mapping->a_ops = &btree_aops;
RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node);
extent_io_tree_init(&BTRFS_I(inode)->io_tree, inode);
BTRFS_I(inode)->io_tree.track_uptodate = 0;
extent_map_tree_init(&BTRFS_I(inode)->extent_tree);
BTRFS_I(inode)->io_tree.ops = &btree_extent_io_ops;
BTRFS_I(inode)->root = fs_info->tree_root;
memset(&BTRFS_I(inode)->location, 0, sizeof(struct btrfs_key));
set_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags);
btrfs_insert_inode_hash(inode);
}
static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info)
{
mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount);
init_rwsem(&fs_info->dev_replace.rwsem);
init_waitqueue_head(&fs_info->dev_replace.replace_wait);
}
static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
{
spin_lock_init(&fs_info->qgroup_lock);
mutex_init(&fs_info->qgroup_ioctl_lock);
fs_info->qgroup_tree = RB_ROOT;
fs_info->qgroup_op_tree = RB_ROOT;
INIT_LIST_HEAD(&fs_info->dirty_qgroups);
fs_info->qgroup_seq = 1;
fs_info->qgroup_ulist = NULL;
fs_info->qgroup_rescan_running = false;
mutex_init(&fs_info->qgroup_rescan_lock);
}
static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
struct btrfs_fs_devices *fs_devices)
{
u32 max_active = fs_info->thread_pool_size;
unsigned int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND;
fs_info->workers =
btrfs_alloc_workqueue(fs_info, "worker",
flags | WQ_HIGHPRI, max_active, 16);
fs_info->delalloc_workers =
btrfs_alloc_workqueue(fs_info, "delalloc",
flags, max_active, 2);
fs_info->flush_workers =
btrfs_alloc_workqueue(fs_info, "flush_delalloc",
flags, max_active, 0);
fs_info->caching_workers =
btrfs_alloc_workqueue(fs_info, "cache", flags, max_active, 0);
/*
* a higher idle thresh on the submit workers makes it much more
* likely that bios will be send down in a sane order to the
* devices
*/
fs_info->submit_workers =
btrfs_alloc_workqueue(fs_info, "submit", flags,
min_t(u64, fs_devices->num_devices,
max_active), 64);
fs_info->fixup_workers =
btrfs_alloc_workqueue(fs_info, "fixup", flags, 1, 0);
/*
* endios are largely parallel and should have a very
* low idle thresh
*/
fs_info->endio_workers =
btrfs_alloc_workqueue(fs_info, "endio", flags, max_active, 4);
fs_info->endio_meta_workers =
btrfs_alloc_workqueue(fs_info, "endio-meta", flags,
max_active, 4);
fs_info->endio_meta_write_workers =
btrfs_alloc_workqueue(fs_info, "endio-meta-write", flags,
max_active, 2);
fs_info->endio_raid56_workers =
btrfs_alloc_workqueue(fs_info, "endio-raid56", flags,
max_active, 4);
fs_info->endio_repair_workers =
btrfs_alloc_workqueue(fs_info, "endio-repair", flags, 1, 0);
fs_info->rmw_workers =
btrfs_alloc_workqueue(fs_info, "rmw", flags, max_active, 2);
fs_info->endio_write_workers =
btrfs_alloc_workqueue(fs_info, "endio-write", flags,
max_active, 2);
fs_info->endio_freespace_worker =
btrfs_alloc_workqueue(fs_info, "freespace-write", flags,
max_active, 0);
fs_info->delayed_workers =
btrfs_alloc_workqueue(fs_info, "delayed-meta", flags,
max_active, 0);
fs_info->readahead_workers =
btrfs_alloc_workqueue(fs_info, "readahead", flags,
max_active, 2);
fs_info->qgroup_rescan_workers =
btrfs_alloc_workqueue(fs_info, "qgroup-rescan", flags, 1, 0);
fs_info->extent_workers =
btrfs_alloc_workqueue(fs_info, "extent-refs", flags,
min_t(u64, fs_devices->num_devices,
max_active), 8);
if (!(fs_info->workers && fs_info->delalloc_workers &&
fs_info->submit_workers && fs_info->flush_workers &&
fs_info->endio_workers && fs_info->endio_meta_workers &&
fs_info->endio_meta_write_workers &&
fs_info->endio_repair_workers &&
fs_info->endio_write_workers && fs_info->endio_raid56_workers &&
fs_info->endio_freespace_worker && fs_info->rmw_workers &&
fs_info->caching_workers && fs_info->readahead_workers &&
fs_info->fixup_workers && fs_info->delayed_workers &&
fs_info->extent_workers &&
fs_info->qgroup_rescan_workers)) {
return -ENOMEM;
}
return 0;
}
static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
struct btrfs_fs_devices *fs_devices)
{
int ret;
struct btrfs_root *log_tree_root;
struct btrfs_super_block *disk_super = fs_info->super_copy;
u64 bytenr = btrfs_super_log_root(disk_super);
int level = btrfs_super_log_root_level(disk_super);
if (fs_devices->rw_devices == 0) {
btrfs_warn(fs_info, "log replay required on RO media");
return -EIO;
}
log_tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
if (!log_tree_root)
return -ENOMEM;
__setup_root(log_tree_root, fs_info, BTRFS_TREE_LOG_OBJECTID);
log_tree_root->node = read_tree_block(fs_info, bytenr,
fs_info->generation + 1,
level, NULL);
if (IS_ERR(log_tree_root->node)) {
btrfs_warn(fs_info, "failed to read log tree");
ret = PTR_ERR(log_tree_root->node);
kfree(log_tree_root);
return ret;
} else if (!extent_buffer_uptodate(log_tree_root->node)) {
btrfs_err(fs_info, "failed to read log tree");
free_extent_buffer(log_tree_root->node);
kfree(log_tree_root);
return -EIO;
}
/* returns with log_tree_root freed on success */
ret = btrfs_recover_log_trees(log_tree_root);
if (ret) {
btrfs_handle_fs_error(fs_info, ret,
"Failed to recover log tree");
free_extent_buffer(log_tree_root->node);
kfree(log_tree_root);
return ret;
}
if (sb_rdonly(fs_info->sb)) {
ret = btrfs_commit_super(fs_info);
if (ret)
return ret;
}
return 0;
}
static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
{
struct btrfs_root *tree_root = fs_info->tree_root;
struct btrfs_root *root;
struct btrfs_key location;
int ret;
BUG_ON(!fs_info->tree_root);
location.objectid = BTRFS_EXTENT_TREE_OBJECTID;
location.type = BTRFS_ROOT_ITEM_KEY;
location.offset = 0;
root = btrfs_read_tree_root(tree_root, &location);
if (IS_ERR(root)) {
ret = PTR_ERR(root);
goto out;
}
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
fs_info->extent_root = root;
location.objectid = BTRFS_DEV_TREE_OBJECTID;
root = btrfs_read_tree_root(tree_root, &location);
if (IS_ERR(root)) {
ret = PTR_ERR(root);
goto out;
}
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
fs_info->dev_root = root;
btrfs_init_devices_late(fs_info);
location.objectid = BTRFS_CSUM_TREE_OBJECTID;
root = btrfs_read_tree_root(tree_root, &location);
if (IS_ERR(root)) {
ret = PTR_ERR(root);
goto out;
}
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
fs_info->csum_root = root;
location.objectid = BTRFS_QUOTA_TREE_OBJECTID;
root = btrfs_read_tree_root(tree_root, &location);
if (!IS_ERR(root)) {
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
fs_info->quota_root = root;
}
location.objectid = BTRFS_UUID_TREE_OBJECTID;
root = btrfs_read_tree_root(tree_root, &location);
if (IS_ERR(root)) {
ret = PTR_ERR(root);
if (ret != -ENOENT)
goto out;
} else {
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
fs_info->uuid_root = root;
}
if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
location.objectid = BTRFS_FREE_SPACE_TREE_OBJECTID;
root = btrfs_read_tree_root(tree_root, &location);
if (IS_ERR(root)) {
ret = PTR_ERR(root);
goto out;
}
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
fs_info->free_space_root = root;
}
return 0;
out:
btrfs_warn(fs_info, "failed to read root (objectid=%llu): %d",
location.objectid, ret);
return ret;
}
/*
* Real super block validation
* NOTE: super csum type and incompat features will not be checked here.
*
* @sb: super block to check
* @mirror_num: the super block number to check its bytenr:
* 0 the primary (1st) sb
* 1, 2 2nd and 3rd backup copy
* -1 skip bytenr check
*/
static int validate_super(struct btrfs_fs_info *fs_info,
struct btrfs_super_block *sb, int mirror_num)
{
u64 nodesize = btrfs_super_nodesize(sb);
u64 sectorsize = btrfs_super_sectorsize(sb);
int ret = 0;
if (btrfs_super_magic(sb) != BTRFS_MAGIC) {
btrfs_err(fs_info, "no valid FS found");
ret = -EINVAL;
}
if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP) {
btrfs_err(fs_info, "unrecognized or unsupported super flag: %llu",
btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
ret = -EINVAL;
}
if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
btrfs_err(fs_info, "tree_root level too big: %d >= %d",
btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);
ret = -EINVAL;
}
if (btrfs_super_chunk_root_level(sb) >= BTRFS_MAX_LEVEL) {
btrfs_err(fs_info, "chunk_root level too big: %d >= %d",
btrfs_super_chunk_root_level(sb), BTRFS_MAX_LEVEL);
ret = -EINVAL;
}
if (btrfs_super_log_root_level(sb) >= BTRFS_MAX_LEVEL) {
btrfs_err(fs_info, "log_root level too big: %d >= %d",
btrfs_super_log_root_level(sb), BTRFS_MAX_LEVEL);
ret = -EINVAL;
}
/*
* Check sectorsize and nodesize first, other check will need it.
* Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here.
*/
if (!is_power_of_2(sectorsize) || sectorsize < 4096 ||
sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) {
btrfs_err(fs_info, "invalid sectorsize %llu", sectorsize);
ret = -EINVAL;
}
/* Only PAGE SIZE is supported yet */
if (sectorsize != PAGE_SIZE) {
btrfs_err(fs_info,
"sectorsize %llu not supported yet, only support %lu",
sectorsize, PAGE_SIZE);
ret = -EINVAL;
}
if (!is_power_of_2(nodesize) || nodesize < sectorsize ||
nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) {
btrfs_err(fs_info, "invalid nodesize %llu", nodesize);
ret = -EINVAL;
}
if (nodesize != le32_to_cpu(sb->__unused_leafsize)) {
btrfs_err(fs_info, "invalid leafsize %u, should be %llu",
le32_to_cpu(sb->__unused_leafsize), nodesize);
ret = -EINVAL;
}
/* Root alignment check */
if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) {
btrfs_warn(fs_info, "tree_root block unaligned: %llu",
btrfs_super_root(sb));
ret = -EINVAL;
}
if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) {
btrfs_warn(fs_info, "chunk_root block unaligned: %llu",
btrfs_super_chunk_root(sb));
ret = -EINVAL;
}
if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) {
btrfs_warn(fs_info, "log_root block unaligned: %llu",
btrfs_super_log_root(sb));
ret = -EINVAL;
}
if (memcmp(fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid,
BTRFS_FSID_SIZE) != 0) {
btrfs_err(fs_info,
"dev_item UUID does not match metadata fsid: %pU != %pU",
fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid);
ret = -EINVAL;
}
/*
* Hint to catch really bogus numbers, bitflips or so, more exact checks are
* done later
*/
if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) {
btrfs_err(fs_info, "bytes_used is too small %llu",
btrfs_super_bytes_used(sb));
ret = -EINVAL;
}
if (!is_power_of_2(btrfs_super_stripesize(sb))) {
btrfs_err(fs_info, "invalid stripesize %u",
btrfs_super_stripesize(sb));
ret = -EINVAL;
}
if (btrfs_super_num_devices(sb) > (1UL << 31))
btrfs_warn(fs_info, "suspicious number of devices: %llu",
btrfs_super_num_devices(sb));
if (btrfs_super_num_devices(sb) == 0) {
btrfs_err(fs_info, "number of devices is 0");
ret = -EINVAL;
}
if (mirror_num >= 0 &&
btrfs_super_bytenr(sb) != btrfs_sb_offset(mirror_num)) {
btrfs_err(fs_info, "super offset mismatch %llu != %u",
btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET);
ret = -EINVAL;
}
/*
* Obvious sys_chunk_array corruptions, it must hold at least one key
* and one chunk
*/
if (btrfs_super_sys_array_size(sb) > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) {
btrfs_err(fs_info, "system chunk array too big %u > %u",
btrfs_super_sys_array_size(sb),
BTRFS_SYSTEM_CHUNK_ARRAY_SIZE);
ret = -EINVAL;
}
if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key)
+ sizeof(struct btrfs_chunk)) {
btrfs_err(fs_info, "system chunk array too small %u < %zu",
btrfs_super_sys_array_size(sb),
sizeof(struct btrfs_disk_key)
+ sizeof(struct btrfs_chunk));
ret = -EINVAL;
}
/*
* The generation is a global counter, we'll trust it more than the others
* but it's still possible that it's the one that's wrong.
*/
if (btrfs_super_generation(sb) < btrfs_super_chunk_root_generation(sb))
btrfs_warn(fs_info,
"suspicious: generation < chunk_root_generation: %llu < %llu",
btrfs_super_generation(sb),
btrfs_super_chunk_root_generation(sb));
if (btrfs_super_generation(sb) < btrfs_super_cache_generation(sb)
&& btrfs_super_cache_generation(sb) != (u64)-1)
btrfs_warn(fs_info,
"suspicious: generation < cache_generation: %llu < %llu",
btrfs_super_generation(sb),
btrfs_super_cache_generation(sb));
return ret;
}
/*
* Validation of super block at mount time.
* Some checks already done early at mount time, like csum type and incompat
* flags will be skipped.
*/
static int btrfs_validate_mount_super(struct btrfs_fs_info *fs_info)
{
return validate_super(fs_info, fs_info->super_copy, 0);
}
/*
* Validation of super block at write time.
* Some checks like bytenr check will be skipped as their values will be
* overwritten soon.
* Extra checks like csum type and incompat flags will be done here.
*/
static int btrfs_validate_write_super(struct btrfs_fs_info *fs_info,
struct btrfs_super_block *sb)
{
int ret;
ret = validate_super(fs_info, sb, -1);
if (ret < 0)
goto out;
if (btrfs_super_csum_type(sb) != BTRFS_CSUM_TYPE_CRC32) {
ret = -EUCLEAN;
btrfs_err(fs_info, "invalid csum type, has %u want %u",
btrfs_super_csum_type(sb), BTRFS_CSUM_TYPE_CRC32);
goto out;
}
if (btrfs_super_incompat_flags(sb) & ~BTRFS_FEATURE_INCOMPAT_SUPP) {
ret = -EUCLEAN;
btrfs_err(fs_info,
"invalid incompat flags, has 0x%llx valid mask 0x%llx",
btrfs_super_incompat_flags(sb),
(unsigned long long)BTRFS_FEATURE_INCOMPAT_SUPP);
goto out;
}
out:
if (ret < 0)
btrfs_err(fs_info,
"super block corruption detected before writing it to disk");
return ret;
}
int open_ctree(struct super_block *sb,
struct btrfs_fs_devices *fs_devices,
char *options)
{
u32 sectorsize;
u32 nodesize;
u32 stripesize;
u64 generation;
u64 features;
struct btrfs_key location;
struct buffer_head *bh;
struct btrfs_super_block *disk_super;
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
struct btrfs_root *tree_root;
struct btrfs_root *chunk_root;
int ret;
int err = -EINVAL;
int num_backups_tried = 0;
int backup_index = 0;
int clear_free_space_tree = 0;
int level;
tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
if (!tree_root || !chunk_root) {
err = -ENOMEM;
goto fail;
}
ret = init_srcu_struct(&fs_info->subvol_srcu);
if (ret) {
err = ret;
goto fail;
}
ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL);
if (ret) {
err = ret;
goto fail_srcu;
}
fs_info->dirty_metadata_batch = PAGE_SIZE *
(1 + ilog2(nr_cpu_ids));
ret = percpu_counter_init(&fs_info->delalloc_bytes, 0, GFP_KERNEL);
if (ret) {
err = ret;
goto fail_dirty_metadata_bytes;
}
ret = percpu_counter_init(&fs_info->dev_replace.bio_counter, 0,
GFP_KERNEL);
if (ret) {
err = ret;
goto fail_delalloc_bytes;
}
INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC);
INIT_LIST_HEAD(&fs_info->trans_list);
INIT_LIST_HEAD(&fs_info->dead_roots);
INIT_LIST_HEAD(&fs_info->delayed_iputs);
INIT_LIST_HEAD(&fs_info->delalloc_roots);
INIT_LIST_HEAD(&fs_info->caching_block_groups);
INIT_LIST_HEAD(&fs_info->pending_raid_kobjs);
spin_lock_init(&fs_info->pending_raid_kobjs_lock);
spin_lock_init(&fs_info->delalloc_root_lock);
spin_lock_init(&fs_info->trans_lock);
spin_lock_init(&fs_info->fs_roots_radix_lock);
spin_lock_init(&fs_info->delayed_iput_lock);
spin_lock_init(&fs_info->defrag_inodes_lock);
spin_lock_init(&fs_info->tree_mod_seq_lock);
spin_lock_init(&fs_info->super_lock);
spin_lock_init(&fs_info->qgroup_op_lock);
spin_lock_init(&fs_info->buffer_lock);
spin_lock_init(&fs_info->unused_bgs_lock);
rwlock_init(&fs_info->tree_mod_log_lock);
mutex_init(&fs_info->unused_bg_unpin_mutex);
mutex_init(&fs_info->delete_unused_bgs_mutex);
mutex_init(&fs_info->reloc_mutex);
mutex_init(&fs_info->delalloc_root_mutex);
seqlock_init(&fs_info->profiles_lock);
INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
INIT_LIST_HEAD(&fs_info->space_info);
INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
INIT_LIST_HEAD(&fs_info->unused_bgs);
btrfs_mapping_init(&fs_info->mapping_tree);
btrfs_init_block_rsv(&fs_info->global_block_rsv,
BTRFS_BLOCK_RSV_GLOBAL);
btrfs_init_block_rsv(&fs_info->trans_block_rsv, BTRFS_BLOCK_RSV_TRANS);
btrfs_init_block_rsv(&fs_info->chunk_block_rsv, BTRFS_BLOCK_RSV_CHUNK);
btrfs_init_block_rsv(&fs_info->empty_block_rsv, BTRFS_BLOCK_RSV_EMPTY);
btrfs_init_block_rsv(&fs_info->delayed_block_rsv,
BTRFS_BLOCK_RSV_DELOPS);
btrfs_init_block_rsv(&fs_info->delayed_refs_rsv,
BTRFS_BLOCK_RSV_DELREFS);
atomic_set(&fs_info->async_delalloc_pages, 0);
atomic_set(&fs_info->defrag_running, 0);
atomic_set(&fs_info->qgroup_op_seq, 0);
atomic_set(&fs_info->reada_works_cnt, 0);
atomic_set(&fs_info->nr_delayed_iputs, 0);
atomic64_set(&fs_info->tree_mod_seq, 0);
fs_info->sb = sb;
fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE;
fs_info->metadata_ratio = 0;
fs_info->defrag_inodes = RB_ROOT;
atomic64_set(&fs_info->free_chunk_space, 0);
fs_info->tree_mod_log = RB_ROOT;
fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */
/* readahead state */
INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
spin_lock_init(&fs_info->reada_lock);
btrfs_init_ref_verify(fs_info);
fs_info->thread_pool_size = min_t(unsigned long,
num_online_cpus() + 2, 8);
INIT_LIST_HEAD(&fs_info->ordered_roots);
spin_lock_init(&fs_info->ordered_root_lock);
fs_info->btree_inode = new_inode(sb);
if (!fs_info->btree_inode) {
err = -ENOMEM;
goto fail_bio_counter;
}
mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);
fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root),
GFP_KERNEL);
if (!fs_info->delayed_root) {
err = -ENOMEM;
goto fail_iput;
}
btrfs_init_delayed_root(fs_info->delayed_root);
btrfs_init_scrub(fs_info);
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
fs_info->check_integrity_print_mask = 0;
#endif
btrfs_init_balance(fs_info);
btrfs_init_async_reclaim_work(&fs_info->async_reclaim_work);
sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE;
sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE);
btrfs_init_btree_inode(fs_info);
spin_lock_init(&fs_info->block_group_cache_lock);
fs_info->block_group_cache_tree = RB_ROOT;
fs_info->first_logical_byte = (u64)-1;
extent_io_tree_init(&fs_info->freed_extents[0], NULL);